@misc{WunderlichTschoepeDuckhorn, author = {Wunderlich, Christian and Tsch{\"o}pe, Constanze and Duckhorn, Frank}, title = {Advanced methods in NDE using machine learning approaches}, series = {44th Annual Review of Progress in Quantitative Nondestructive Evaluation, Provo, Utah, USA, 16-21 July 2017}, volume = {37}, journal = {44th Annual Review of Progress in Quantitative Nondestructive Evaluation, Provo, Utah, USA, 16-21 July 2017}, publisher = {AIP Publishing}, address = {College Park, Maryland}, issn = {0094-243X}, doi = {10.1063/1.5031519}, pages = {1 -- 8}, abstract = {Machine learning (ML) methods and algorithms have been applied recently with great success in quality control and predictive maintenance. Its goal to build new and/or leverage existing algorithms to learn from training data and give accurate predictions, or to find patterns, particularly with new and unseen similar data, fits perfectly to Non-Destructive Evaluation. The advantages of ML in NDE are obvious in such tasks as pattern recognition in acoustic signals or automated processing of images from X-ray, Ultrasonics or optical methods. Fraunhofer IKTS is using machine learning algorithms in acoustic signal analysis. The approach had been applied to such a variety of tasks in quality assessment. The principal approach is based on acoustic signal processing with a primary and secondary analysis step followed by a cognitive system to create model data. Already in the second analysis steps unsupervised learning algorithms as principal component analysis are used to simplify data structures. In the cognitive part of the software further unsupervised and supervised learning algorithms will be trained. Later the sensor signals from unknown samples can be recognized and classified automatically by the algorithms trained before. Recently the IKTS team was able to transfer the software for signal processing and pattern recognition to a small printed circuit board (PCB). Still, algorithms will be trained on an ordinary PC; however, trained algorithms run on the Digital Signal Processor and the FPGA chip. The identical approach will be used for pattern recognition in image analysis of OCT pictures. Some key requirements have to be fulfilled, however. A sufficiently large set of training data, a high signal-to-noise ratio, and an optimized and exact fixation of components are required. The automated testing can be done subsequently by the machine. By integrating the test data of many components along the value chain further optimization including lifetime and durability prediction based on big data becomes possible, even if components are used in different versions or configurations. This is the promise behind German Industry 4.0.}, language = {en} } @inproceedings{TschoepeHentschelWolffetal., author = {Tsch{\"o}pe, Constanze and Hentschel, Dieter and Wolff, Matthias and Eichner, Matthias and Hoffmann, R{\"u}diger}, title = {Classification of non-speech acoustic signals using structure models}, series = {Proceedings, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 17 - 21, 2004, Montreal, Canada, vol. 5}, volume = {5}, booktitle = {Proceedings, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 17 - 21, 2004, Montreal, Canada, vol. 5}, publisher = {IEEE Operations Center}, address = {Piscataway, NJ}, isbn = {0-7803-8484-9}, doi = {10.1109/ICASSP.2004.1327195}, pages = {653 -- 656}, abstract = {Non-speech acoustic signals are widely used as the input of systems for non-destructive testing. In this rapidly growing field, the signals have an increasing complexity leading to the fact that powerful models are required. Methods like DTW and HMM, which are established in speech recognition, have been successfully used but are not sufficient in all cases. We propose the application of generalized structured Markov graphs (SMG). We describe a task independent structure learning technique which automatically adapts the models to the structure of the test signals. We demonstrate that our solution outperforms hand-tuned HMM structures in terms of class discrimination by two case studies using data from real applications.}, language = {en} } @inproceedings{WolffSchubertHoffmannetal., author = {Wolff, Matthias and Schubert, R. and Hoffmann, R{\"u}diger and Tsch{\"o}pe, Constanze and Schulze, E. and Neun{\"u}bel, H.}, title = {Experiments in Acoustic Structural Health Monitoring of Airplane Parts}, series = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2008), 30.3.-4.4.2008, Las Vegas, USA}, booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2008), 30.3.-4.4.2008, Las Vegas, USA}, publisher = {IEEE}, isbn = {978-1-4244-1483-3}, doi = {10.1109/ICASSP.2008.4518040}, pages = {2037 -- 2040}, language = {en} } @incollection{HoffmannEichnerKordonetal., author = {Hoffmann, R{\"u}diger and Eichner, Matthias and Kordon, Ulrich and Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {Anwendung von Spracherkennungsalgorithmen auf nichtsprachliche akustische Signale}, series = {Sprachsignalverarbeitung : Analyse und Anwendungen ; zum 65. Geburtstag von Klaus Fellbaum}, booktitle = {Sprachsignalverarbeitung : Analyse und Anwendungen ; zum 65. Geburtstag von Klaus Fellbaum}, editor = {Hentschel, Christian}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-940046-02-4}, pages = {46 -- 57}, language = {de} } @inproceedings{StrechaWolffDuckhornetal., author = {Strecha, Guntram and Wolff, Matthias and Duckhorn, Frank and Wittenberg, S{\"o}ren and Tsch{\"o}pe, Constanze}, title = {The HMM synthesis algorithm of an embedded unified speech recognizer and synthesizer}, series = {Proceedings of the Annual Conference of the International Speech Communication Association 2009, Interspeech 2009, 6 - 10 September, 2009, Brighton, UK}, booktitle = {Proceedings of the Annual Conference of the International Speech Communication Association 2009, Interspeech 2009, 6 - 10 September, 2009, Brighton, UK}, publisher = {ISCA}, address = {Brighton}, pages = {1763 -- 1766}, language = {en} } @misc{PuschCherifFarooqetal., author = {Pusch, T. and Cherif, Chokri and Farooq, Aamir and Wittenberg, S{\"o}ren and Wolff, Matthias and Hoffmann, R{\"u}diger and Tsch{\"o}pe, Constanze}, title = {Fehlerfr{\"u}herkennung an Textilmaschinen mit Hilfe der K{\"o}rperschallanalyse}, series = {Melliand Textilberichte}, volume = {90}, journal = {Melliand Textilberichte}, number = {3}, issn = {0341-0781}, pages = {113 -- 115}, language = {de} } @inproceedings{WolffTschoepe, author = {Wolff, Matthias and Tsch{\"o}pe, Constanze}, title = {Pattern recognition for sensor signals}, series = {Proceedings of the IEEE Sensors Conference 2009, Christchurch, New Zealand, 25 - 28 October 2009}, booktitle = {Proceedings of the IEEE Sensors Conference 2009, Christchurch, New Zealand, 25 - 28 October 2009}, publisher = {IEEE}, address = {Piscataway, NJ}, isbn = {978-1-424-44548-6}, doi = {10.1109/ICSENS.2009.5398338}, pages = {665 -- 668}, language = {en} } @phdthesis{Wolff, author = {Wolff, Matthias}, title = {Akustische Mustererkennung}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-942710-14-5}, pages = {XIV, 313}, language = {de} } @misc{LiKraljevskiMeyeretal., author = {Li, Huajian and Kraljevski, Ivan and Meyer, Paul and Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {YOLO-ICP : deep learning integrated pose estimation for bin-picking of multiple objects}, series = {2024 IEEE SENSORS, Proceedings, Kobe, Japan, 2024}, journal = {2024 IEEE SENSORS, Proceedings, Kobe, Japan, 2024}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, address = {Piscataway, New Jersey}, isbn = {979-8-3503-6351-7}, doi = {10.1109/SENSORS60989.2024.10784539}, pages = {1 -- 4}, abstract = {In this paper, we present a novel deep learning-integrated pipeline called YOLO-ICP that aims to estimate the six degree of freedom (6-DoF) pose of objects using RGB-D sensors and does not require pose labels to train deep learning networks. YOLO-ICP integrates a real-time object detection algorithm with a point cloud registration method to estimate the pose of multiple objects. We evaluated our approach by quantitatively comparing it with baseline models on the OccludedLINEMOD dataset. Experimental results illustrate that our approach outperforms baseline models in challenging scenarios with textureless and occluded objects. In particular, our pipeline shows superior performance when dealing with small and symmetric objects in terms of the ADD(-S) metric.}, language = {en} } @misc{SchmidtHildebrandKraljevskietal., author = {Schmidt, Ralph Rudi and Hildebrand, Jorg and Kraljevski, Ivan and Duckhorn, Frank and Tsch{\"o}pe, Constanze}, title = {A study for laser additive manufacturing quality and material classification using machine learning}, series = {2022 IEEE sensors}, journal = {2022 IEEE sensors}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, address = {Piscataway, New Jersey}, isbn = {978-1-6654-8464-0}, issn = {2168-9229}, doi = {10.1109/SENSORS52175.2022.9967311}, pages = {1 -- 4}, abstract = {This paper demonstrates the use of acoustic emissions (AEs) to monitor the quality, and material used, for the laser additive manufacturing (LAM) process with steel and copper wire. Layers of deposited material (steel or copper) were created using LAM. The quality of these layers was either good or unstable. The AEs were recorded using three sensors, one microphone, and two structure-borne sound probes. The recorded signals were processed and transformed using the fast Fourier method. Then models were trained with the processed data and evaluated using a fivefold cross-validation. Results show that it is possible to accurately classify the materials used during LAM (up to a balanced accuracy [BAcc] score of 0.99). Also, the process quality could be classified with a BAcc score of up to 0.81. Overall, the results are promising, but further research and data collection are necessary for a proper validation of our results.}, language = {en} } @misc{OpitzWunderlichBendjusetal., author = {Opitz, Joerg and Wunderlich, Christian and Bendjus, B. and Cikalova, U. and Wolf, C. and Naumann, S. and Lehmann, A. and Barth, M. and Duckhorn, Frank and K{\"o}hler, B. and Tsch{\"o}ke, K. and Windisch, T. and Tsch{\"o}pe, Constanze and Moritz, T. and Scheithauer, U.}, title = {Materialdiagnose und integrale Pr{\"u}fverfahren f{\"u}r keramische Bauteile}, series = {Keramische Zeitschrift}, volume = {68}, journal = {Keramische Zeitschrift}, number = {4-5}, publisher = {Springer Science and Business Media LLC}, address = {Berlin ; Heidelberg}, issn = {0023-0561}, doi = {10.1007/BF03400267}, pages = {249 -- 254}, abstract = {Hochleistungskeramiken findet man heute h{\"a}ufig als kritische Komponente in neuentwickelten Systemen f{\"u}r Zukunftsanwendungen. Die Zuverl{\"a}ssigkeit des gesamten Systems basiert hierbei oft auf der kritischen keramischen Komponente. F{\"u}r diese oft neuentwickelten keramischen Materialien werden neue Methoden f{\"u}r die Prozesssteuerung, Materialdiagnostik und Struktur{\"u}berwachung ben{\"o}tigt. In diesem Artikel werden drei f{\"u}r die Keramikcharakterisierung am Fraunhofer-Institut f{\"u}r Keramische Technologien und Systeme IKTS weiter entwickelte Technologien und Verfahren beschrieben und deren Einsatz anhand von Beispielen illustriert. Dazu werden die Laser-Speckle-Photometrie, die optische Koh{\"a}renztomographie und die Klanganalyse in Kombination mit einer entsprechenden akustischen Mustererkennung als leistungsf{\"a}hige Verfahren f{\"u}r die Materialdiagnostik im Bereich der keramischen Materialien vorgestellt.}, language = {de} } @misc{KraljevskiDuckhornSobeetal., author = {Kraljevski, Ivan and Duckhorn, Frank and Sobe, Daniel and Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {Speech-to-text in upper sorbian : current state}, series = {Elektronische Sprachsignalverarbeitung 2025 : Tagungsband der 36. Konferenz Halle/Saale, 5.-7. M{\"a}rz 2025}, journal = {Elektronische Sprachsignalverarbeitung 2025 : Tagungsband der 36. Konferenz Halle/Saale, 5.-7. M{\"a}rz 2025}, editor = {Grawunder, Sven}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-803-9}, issn = {0940-6832}, pages = {109 -- 116}, abstract = {This study presents recent advancements in Upper Sorbian Speech-to-Text (STT) technology. We provide an overview of the Sorbian languages, the available speech and language resources, and the development of an STT system based on a traditional approach, which includes acoustic, pronunciation, and language modeling. Due to the scarcity of resources for Sorbian languages, our approach leverages sub-word and word-class modeling techniques. The word-class modeling is based on Finite-State Transducer definitions, which are applicable to both offline text parsing and integration into the decoding graph of the STT system. Word-class parsing is performed on the speech corpus and utilized for language modeling with complete words, sub-word units, or both. Additionally, the same definitions can be applied to Named Entity Recognition during the post-processing of recognized transcriptions. This approach significantly reduces out-of-vocabulary words and enables greater customization of the recognizer for domain-specific applications. The system was implemented for the real-time transcription of church sermon broadcasts in Upper Sorbian. The domain-specific system achieved performance comparable to fine-tuned OpenAI Whisper models developed also by other initiatives while also providing a resource-efficient solution with semantically tagged recognition results.}, language = {en} } @misc{KraljevskiDuckhornSobeetal., author = {Kraljevski, Ivan and Duckhorn, Frank and Sobe, Daniel and Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {Preserving Language Heritage Through Speech Technology: The Case of Upper Sorbian}, series = {Speech and Computer, SPECOM 2024, Belgrade, Serbia, 25-28 November 2024}, journal = {Speech and Computer, SPECOM 2024, Belgrade, Serbia, 25-28 November 2024}, editor = {Karpov, Alexey and Delic, Vlado}, publisher = {Springer Nature Switzerland, Cham}, isbn = {978-3-031-77960-2}, doi = {10.1007/978-3-031-77961-9_1}, pages = {3 -- 22}, abstract = {The modern world is facing a crisis with the rapid disappearance of endangered languages, which poses a serious threat to global cultural diversity. Speech Technologies and Artificial Intelligence present promising opportunities to address this crisis by supporting the documentation, revitalization, and everyday use of these vulnerable languages. However, despite recent and remarkable advancements in speech technology, significant challenges persist, particularly for languages with very limited resources and unique linguistic features. This paper details the development of Upper Sorbian speech technologies, focusing on the creation of a practical Speech-to-Text (STT) system as a versatile tool for language preservation. The study explores the current state of Sorbian languages and underscores collaborative efforts with the Foundation for the Sorbian People. Through a series of pilot and successive projects, each phase has contributed to the steady advancement of speech recognition modules and supporting tools, improving their performance, effectiveness and practical usability.}, language = {en} } @misc{SaeltzerTschoepeWolff, author = {Saeltzer, Gerhard and Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {Vorrichtung und Verfahren zur Bestimmung eines medizinischen Gesundheitsparameters eines Probanden mittels Stimmanalyse}, pages = {31}, abstract = {Eine Vorrichtung zur Bestimmung eines Gesundheitsparameters eines Probanden mittels Stimmauswertung umfasst eine Verarbeitungseinrichtung, die ausgebildet ist, um eine digitalisierte Sprechprobe des Probanden basierend auf individuellen Modellparametern auszuwerten, um eine Messinformation zu erhalten, die innerhalb eines Toleranzbereichs auf einem Momentanwert des Gesundheitsparameters des Probanden basiert, wobei die individuellen Modellparameter einen funktionalen Zusammenhang zwischen der Sprechprobe oder von der Sprechprobe abgeleiteten Sprechmerkmalen und einem zugeordneten, momentanen Gesundheitsparameter angeben.}, language = {de} } @misc{WolffRoemerTschoepeetal., author = {Wolff, Matthias and R{\"o}mer, Ronald and Tsch{\"o}pe, Constanze and Hentschel, Dieter}, title = {Method and Device for Controlling the Behavior of Systems}, language = {en} } @inproceedings{TschoepeWolff, author = {Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {Automatic decision making in SHM using hidden Markov models}, series = {18th International Conference on Database and Expert Systems Applications (DEXA 2007), Regensburg, September 3-7, 2007}, booktitle = {18th International Conference on Database and Expert Systems Applications (DEXA 2007), Regensburg, September 3-7, 2007}, publisher = {IEEE}, doi = {10.1109/DEXA.2007.138}, pages = {307 -- 311}, language = {en} } @misc{TschoepeWolffHoffmann, author = {Tsch{\"o}pe, Constanze and Wolff, Matthias and Hoffmann, R{\"u}diger}, title = {Akustische Mustererkennung f{\"u}r die ZfP}, series = {MP Materials Testing}, volume = {51}, journal = {MP Materials Testing}, number = {10}, issn = {0025-5300}, pages = {701 -- 704}, language = {de} } @misc{LeithoffDilgerDuckhornetal., author = {Leithoff, Ruben and Dilger, Nikolas and Duckhorn, Frank and Blume, Stefan and Lembcke, Dario and Tsch{\"o}pe, Constanze and Herrmann, Christoph and Dr{\"o}der, Klaus}, title = {Inline monitoring of battery electrode lamination processes based on acoustic measurements}, series = {Batteries}, volume = {7}, journal = {Batteries}, number = {1}, publisher = {MDPI AG}, address = {Basel}, issn = {2313-0105}, doi = {10.3390/batteries7010019}, pages = {1 -- 21}, abstract = {Due to the energy transition and the growth of electromobility, the demand for lithium-ion batteries has increased in recent years. Great demands are being placed on the quality of battery cells and their electrochemical properties. Therefore, the understanding of interactions between products and processes and the implementation of quality management measures are essential factors that requires inline capable process monitoring. In battery cell lamination processes, a typical problem source of quality issues can be seen in missing or misaligned components (anodes, cathodes and separators). An automatic detection of missing or misaligned components, however, has not been established thus far. In this study, acoustic measurements to detect components in battery cell lamination were applied. Although the use of acoustic measurement methods for process monitoring has already proven its usefulness in various fields of application, it has not yet been applied to battery cell production. While laminating battery electrodes and separators, acoustic emissions were recorded. Signal analysis and machine learning techniques were used to acoustically distinguish the individual components that have been processed. This way, the detection of components with a balanced accuracy of up to 83\% was possible, proving the feasibility of the concept as an inline capable monitoring system.}, language = {en} } @misc{LieskeDuckhornTschoepeetal., author = {Lieske, Uwe and Duckhorn, Frank and Tsch{\"o}pe, Constanze and Harig, Paul and Pallmer, Matthias and R{\"o}der, Olaf and R{\"o}der, Elisabeth}, title = {Verfahren zur akustischen Detektion von Schadinsekten bei der Getreide- und Saatgutlagerung}, series = {DGZfP-Jahrestagung Zerst{\"o}rungsfreie Materialpr{\"u}fung 2017 : Kurzfassungen der Vortr{\"a}ge und Posterbeitr{\"a}ge : 22.-24. Mai 2017, Koblenz}, journal = {DGZfP-Jahrestagung Zerst{\"o}rungsfreie Materialpr{\"u}fung 2017 : Kurzfassungen der Vortr{\"a}ge und Posterbeitr{\"a}ge : 22.-24. Mai 2017, Koblenz}, publisher = {Deutsche Gesellschaft f{\"u}r Zerst{\"o}rungsfreie Pr{\"u}fung e.V.}, address = {Berlin}, pages = {2}, abstract = {Getreide bildet eine der wichtigsten Grundlagen f{\"u}r die menschliche und tierische Ern{\"a}hrung. Wie jedes andere pflanzliche Produkt, so ist jedoch Getreide auch Nahrungsquelle f{\"u}r zahlreiche Insekten, die w{\"a}hrend des Pflanzenwachstums und der Lagerung das Korn befallen k{\"o}nnen. J{\"a}hrlich werden etwa 10 \% der weltweiten Getreideernte durch Schadinsekten vernichtet. In der Praxis wird der Befall mit Schadinsekten im Rahmen von Stichproben durch visuelle Inspektion, Sieben oder Aufschwemmen der Getreidek{\"o}rner dokumentiert. Es werden auch einfache Handger{\"a}te mit Mikrofon und Verst{\"a}rker eingesetzt, um Sch{\"a}dlingsbefall durch Fressger{\"a}usche manuell zu erkennen. Eine fr{\"u}hzeitige Diagnose des Auftretens von Vorratssch{\"a}dlingen ist f{\"u}r die Einleitung von Gegenmaßnahmen und die Begrenzung des Schadens von großer Bedeutung. Das hier vorgestellte Verfahren bietet die M{\"o}glichkeit, die auftretenden Ger{\"a}usche automatisiert zu analysieren, und erm{\"o}glicht so eine schnelle und zuverl{\"a}ssige Erkennung von Schadinsekten. Im Rahmen der Untersuchungen wurden die auftretenden Ger{\"a}usche von Schadinsekten in den verschiedenen Entwicklungsstadien analysiert und eine geeignete Signalerfassungshardware f{\"u}r den Feldeinsatz entwickelt. Mit den implementierten Signalverarbeitungsalgorithmen der akustischen Mustererkennung erfolgt die automatisierte Auswertung und Klassifizierung der Sch{\"a}dlingsger{\"a}usche. Das Verfahren, die Hardware und die Messergebnisse werden vorgestellt.}, language = {de} } @incollection{KordonWolffTschoepe, author = {Kordon, Ulrich and Wolff, Matthias and Tsch{\"o}pe, Constanze}, title = {Mustererkennung f{\"u}r Sensorsignale}, editor = {Gerlach, Gerald}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-941298-55-2}, pages = {69 -- 78}, language = {de} } @misc{TschoepeWolff, author = {Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {Statistical Classifiers for Structural Health Monitoring}, series = {IEEE sensors journal}, volume = {9}, journal = {IEEE sensors journal}, number = {11}, issn = {1530-437X}, doi = {10.1109/JSEN.2009.2019330}, pages = {1567 -- 1576}, language = {en} }